Reflect-R1 introduces the first evidence-driven self-correction framework for long video understanding using a three-stage pipeline, stage-decoupled RL via SD-GRPO, and a 120K dataset to achieve SOTA on VideoMME and LongVideoBench.
arXiv preprint arXiv:2601.06224 (2026)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
DeP mitigates MLLM hallucinations by dynamically perturbing text prompts to identify and reinforce stable visual evidence regions while counteracting language prior biases using attention variance and logit statistics.
citing papers explorer
-
Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding
Reflect-R1 introduces the first evidence-driven self-correction framework for long video understanding using a three-stage pipeline, stage-decoupled RL via SD-GRPO, and a 120K dataset to achieve SOTA on VideoMME and LongVideoBench.
-
Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
DeP mitigates MLLM hallucinations by dynamically perturbing text prompts to identify and reinforce stable visual evidence regions while counteracting language prior biases using attention variance and logit statistics.